# Knowledge Diversion for Efficient Morphology Control and Policy Transfer

arXiv: https://arxiv.org/abs/2512.09796 · HTML: https://mlsanity.com/paper/2512.09796/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 10 Dec 2025.

## Builds on (most cited first, 30 of 30)

- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning](https://mlsanity.com/paper/1803.11347/) (2018)
- [Contextual Markov Decision Processes](https://mlsanity.com/paper/1502.02259/) (2015)
- [Embodied Intelligence via Learning and Evolution](https://mlsanity.com/paper/2102.02202/) (2021)
- [Multi-Task Reinforcement Learning with Soft Modularization](https://mlsanity.com/paper/2003.13661/) (2020)
- [One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control](https://mlsanity.com/paper/2007.04976/) (2020)
- [Orthogonalizing Convolutional Layers with the Cayley Transform](https://mlsanity.com/paper/2104.07167/) (2021)
- [MetaMorph: Learning Universal Controllers with Transformers](https://mlsanity.com/paper/2203.11931/) (2022)
- [Trivializations for Gradient-Based Optimization on Manifolds](https://mlsanity.com/paper/1909.09501/) (2019)
- [Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity](https://mlsanity.com/paper/1902.05546/) (2019)
- [My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control](https://mlsanity.com/paper/2010.01856/) (2020)
- [GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots](https://mlsanity.com/paper/2209.05309/) (2022)
- [On Transforming Reinforcement Learning by Transformer: The Development Trajectory](https://mlsanity.com/paper/2212.14164/) (2022)
- [Learngene: From Open-World to Your Learning Task](https://mlsanity.com/paper/2106.06788/) (2021)
- [AnyMorph: Learning Transferable Polices By Inferring Agent Morphology](https://mlsanity.com/paper/2206.12279/) (2022)
- [GET-Zero: Graph Embodiment Transformer for Zero-shot Embodiment Generalization](https://mlsanity.com/paper/2407.15002/) (2024)
- [Programmatically Grounded, Compositionally Generalizable Robotic Manipulation](https://mlsanity.com/paper/2304.13826/) (2023)
- [Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models](https://mlsanity.com/paper/2305.02279/) (2023)
- [Universal Morphology Control via Contextual Modulation](https://mlsanity.com/paper/2302.11070/) (2023)
- [Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms](https://mlsanity.com/paper/2103.03697/) (2021)
- [CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation](https://mlsanity.com/paper/2410.09400/) (2024)
- [WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models](https://mlsanity.com/paper/2406.17503/) (2024)
- [Transformer as Linear Expansion of Learngene](https://mlsanity.com/paper/2312.05614/) (2023)
- [Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control](https://mlsanity.com/paper/2402.06570/) (2024)
- [KIND: Knowledge Integration and Diversion for Training Decomposable Models](https://mlsanity.com/paper/2408.07337/) (2024)
- [GCNT: Graph-Based Transformer Policies for Morphology-Agnostic Reinforcement Learning](https://mlsanity.com/paper/2505.15211/) (2025)
- [DivControl: Knowledge Diversion for Controllable Image Generation](https://mlsanity.com/paper/2507.23620/) (2025)
- [FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models](https://mlsanity.com/paper/2409.19289/) (2024)
- [Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidance](https://mlsanity.com/paper/2507.06615/) (2025)

## Built on by (most cited first, 1 of 1)

- [Bridging Body and Brain: Gene-Driven Morphology--Control Co-Design](https://mlsanity.com/paper/2609.31329/) (2026)

## Abstract (arXiv)

Universal morphology control aims to learn a universal policy that generalizes across heterogeneous agent morphologies, with Transformer-based controllers emerging as a popular choice. However, such architectures incur substantial computational costs, resulting in high deployment overhead, and existing methods exhibit limited cross-task generalization, necessitating training from scratch for each new task. To this end, we propose DivMorph, a modular training paradigm that leverages knowledge diversion to learn decomposable controllers. DivMorph factorizes randomly initialized Transformer weights into factor units via SVD prior to training and employs dynamic soft gating to modulate these units based on task and morphology embeddings, separating them into shared textitlearngenes and morphology- and task-specific textittailors, thereby achieving knowledge disentanglement. By selectively activating relevant components, DivMorph enables scalable and efficient policy deployment while supporting effective policy transfer to novel tasks. Extensive experiments demonstrate that DivMorph achieves state-of-the-art performance, achieving a 3× improvement in sample efficiency over direct finetuning for cross-task transfer and a 17× reduction in model size for single-agent deployment.